Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2736 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3706. Min Range: -6.3706
Max Act: 6.3706. Min Act: -0.1700
Data Index: 273842 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3706. Min Range: -6.3706
Max Act: 6.1831. Min Act: -0.1700
Data Index: 975073 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3706. Min Range: -6.3706
Max Act: 6.0894. Min Act: -0.1700
Data Index: 5556088 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3706. Min Range: -6.3706
Max Act: 6.0581. Min Act: -0.1700
Data Index: 6012020 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9956. Min Act: -0.1700
Data Index: 6094061 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9956. Min Act: -0.1700
Data Index: 7396787 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9956. Min Act: -0.1700
Data Index: 1682655 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9644. Min Act: -0.1700
Data Index: 142499 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9331. Min Act: -0.1700
Data Index: 3994156 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9331. Min Act: -0.1700
Data Index: 8203310 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9019. Min Act: -0.1700
Data Index: 7019071 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.9019. Min Act: -0.1700
Data Index: 7817605 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.8394. Min Act: -0.1700
Data Index: 7563928 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.8081. Min Act: -0.1700
Data Index: 8748769 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.8394. Min Act: -0.1700
Data Index: 6583880 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.8394. Min Act: -0.1700
Data Index: 2354312 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.8081. Min Act: -0.1700
Data Index: 5893307 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.7769. Min Act: -0.1700
Data Index: 6851085 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.8394. Min Act: -0.1700
Data Index: 1236676 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3706. Min Range: -6.3706
Max Act: 5.8081. Min Act: -0.1700
Data Index: 4149779 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19